Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16312
    Prev
    Next
    INDEX
    Explanations

    parts of scientific names for organisms.

    oai_token-act-pair · gemini-2.0-flash

    words in scientific texts

    np_token-act-pair-logits · gemini-2.0-flash

    scientific names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sabato
    -0.55
     domenica
    -0.54
     laboratory
    -0.51
    noin
    -0.50
     poveznice
    -0.49
     parallel
    -0.49
    生活的
    -0.48
     livs
    -0.48
     Parallel
    -0.47
    łki
    -0.46
    POSITIVE LOGITS
    GEBURTSDATUM
    0.74
    帖最后由
    0.72
     CreateTagHelper
    0.72
    typeorm
    0.69
    awaiter
    0.68
    transQ
    0.64
     HomeController
    0.60
    featureID
    0.60
    তথ্যসূত্র
    0.60
    LayoutPanel
    0.59
    Activations Density 0.960%

    No Known Activations